Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the application or enforcement of rules or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    apply to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    estra
    -0.50
     нена
    -0.47
     Weinberg
    -0.46
    ESTRA
    -0.45
     Thornton
    -0.44
     ghosts
    -0.43
     Monfieur
    -0.43
    Ghost
    -0.42
    otor
    -0.42
     hänen
    -0.42
    POSITIVE LOGITS
     apply
    1.58
     applies
    1.51
    apply
    1.48
     Apply
    1.45
    Apply
    1.41
    Applies
    1.32
     APPLY
    1.29
     Applies
    1.24
    APPLY
    1.24
     applied
    1.24
    Act Density 0.026%

    No Known Activations